@article{jimenez2023,

title = {Streaming big time series forecasting based on nearest similar patterns with application to energy consumption},

author = {P. Jiménez-Herrera and L. Melgar-García and G. Asencio-Cortés and A. Troncoso},

url = {https://academic.oup.com/jigpal/advance-article-abstract/doi/10.1093/jigpal/jzac017/6534493?redirectedFrom=fulltext},

doi = {https://doi.org/10.1093/jigpal/jzac017},

year  = {2023},

date = {2023-01-01},

journal = {Logic Journal of the IGPL},

volume = {31},

number = {2},

pages = {255-270},

abstract = {This work presents a novel approach to forecast streaming big time series based on nearest similar patterns. This approach combines a clustering algorithm with a classifier and the nearest neighbors algorithm. It presents two separate stages: offline and online. The offline phase is for training and finding the best models for clustering, classification and the nearest neighbors algorithm. The online phase is to predict big time series in real time. In the offline phase, data are divided into clusters and a forecasting model based on the nearest neighbors is trained for each cluster. In addition, a classifier is trained using the cluster assignments previously generated by the clustering algorithm. In the online phase, the classifier predicts the cluster label of an instance, and the proper nearest neighbors model according to the predicted cluster label is applied to obtain the final prediction using the similar patterns. The algorithm is able to be updated incrementally for online learning from data streams. Results are reported using electricity consumption with a granularity of 10 minutes for 4-hour-ahead forecasting and compared with well-known online benchmark learners, showing a remarkable improvement in prediction accuracy.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{castan2022,

title = {A new hybrid method for predicting univariate and multivariate time series based on pattern forecasting},

author = {M.A. Castán-Lascorz and P. Jiménez-Herrera and A. Troncoso and G. Asencio-Cortés},

url = {https://www.sciencedirect.com/science/article/pii/S0020025521012226?via%3Dihub},

doi = {10.1016/j.ins.2021.12.001},

year  = {2022},

date = {2022-01-01},

journal = {Information Sciences},

volume = {586},

pages = {611--627},

abstract = {Time series forecasting has become indispensable for multiple applications and industrial processes. Currently, a large number of algorithms have been developed to forecast time series, all of which are suitable depending on the characteristics and patterns to be inferred in each case. In this work, a new algorithm is proposed to predict both univariate and multivariate time series based on a combination of clustering, classification and forecasting techniques. The main goal of the proposed algorithm is first to group windows of time series values with similar patterns by applying a clustering process. Then, a specific forecasting model for each pattern is built and training is only conducted with the time windows corresponding to that pattern. The new algorithm has been designed using a flexible framework that allows the model to be generated using any combination of approaches within multiple machine learning techniques. To evaluate the model, several experiments are carried out using different configurations of the clustering, classification and forecasting methods that the model consists of. The results are analyzed and compared to classical prediction models, such as autoregressive, integrated, moving average and Holt-Winters models, to very recent forecasting methods, including deep, long short-term memory neural networks, and to well-known methods in the literature, such as k nearest neighbors, classification and regression trees, as well as random forest.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}